most citedMacro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder

3 citations · 4 across the 2 of their papers we have counts for

collaborators

2 papers

cs.LG2019★ 3 cited

Macro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder

Heecheol Kim, Masanori Yamada, Kosuke Miyoshi +1

One problem in the application of reinforcement learning to real-world problems is the curse of dimensionality on the action space. Macro actions, a sequence of primitive actions,…

stat.ML2019★ 1 cited

FAVAE: Sequence Disentanglement using Information Bottleneck Principle

Masanori Yamada, Heecheol Kim, Kosuke Miyoshi +1

We propose the factorized action variational autoencoder (FAVAE), a state-of-the-art generative model for learning disentangled and interpretable representations from sequential da…